Publication

A novel machine learning based method for deepfake video detection in social media

Mitra, Alakananda
; 
Mohanty, Saraju P.
; 
Corcoran, Peter
; 
Kougianos, Elias
Thumbnail Image
Files
Thumbnail Image
09426086.pdf
Adobe PDF, 605.27 KB
Repository DOI
Publication Date
2021-05-12
Keywords
Deepfake, Deep Learning, Depthwise Separable Convolution, Convolutional Neural Network (CNN), Transfer Learning, Social Media, Compressed Video
Type
Conference Paper
Downloads
Show all metadata
Citation
Mitra, Alakananda, Mohanty, Saraju P., Corcoran, Peter, & Kougianos, Elias. (2020). A novel machine learning based method for deepfake video detection in social media. Paper presented at the 2020 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), Chennai, India, 14-16 December, doi:10.1109/iSES50453.2020.00031
Abstract
With the advent of deepfake videos, video forgery has become a serious threat. Videos in social media are the most common and serious targets. There are some existing works for detecting deepfake videos but very few attempts have been made for videos in social media. This paper presents a neural network based method to detect fake videos. A model, consisting of a convolutional neural network (CNN) and a classifier network is proposed. Three different structures, XceptionNet, InceptionV3 and Resnet50 have been considered as the CNN modules and a comparative study has been made. Xception Net has been chosen in the proposed model and paired with the proposed classifier for classification. We used the FaceForensics++ dataset to reach the best model. Our model integrated in the algorithm detects compressed videos in social media.
Funder
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Publisher DOI
10.1109/iSES50453.2020.00031
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland
cbn
Collections
Electrical and Electronic Engineering (Conference Papers)